Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Constraint-Following on ComplexInstruct & CoDI (Level 4)
Loading...
69.7
ISR
DVR_WS
46.196
52.298
58.4
64.502
Oct 16, 2024
ISR
Updated 4d ago
Evaluation Results
Method
Method
Links
ISR
DVR_WS
Backbone=Llama-3.1-8B-...
2024.10
69.7
DVR_CS
Backbone=Llama-3.1-8B-...
2024.10
69.5
CRITIC
Backbone=Llama-3.1-8B-...
2024.10
64.4
ReAct
Backbone=Llama-3.1-8B-...
2024.10
60.7
R-Sample
Backbone=Llama-3.1-8B-...
2024.10
60.4
Vanilla
Backbone=Llama-3.1-8B-...
2024.10
50.1
Reflxion
Backbone=Llama-3.1-8B-...
2024.10
49.8
BSM
Backbone=Llama-3.1-8B-...
2024.10
47.5
U-SC
Backbone=Llama-3.1-8B-...
2024.10
47.1
Feedback
Search any
task
Search any
task